I am looking at the effect of delivery of feedback, type of feedback and timing of feedback on job performance.

A univariate analysis gives me different significant readings for each variable than running a separate one way anova for each variable (so 3 times in total).

Which do I run??

  • 1
    $\begingroup$ Do you mean one univariate analysis or one univariate analysis for each group? $\endgroup$ – Pere Sep 14 '17 at 16:11
  • $\begingroup$ Can you give some more details? It sounds like you want to predict job performance from feedback delivery, feedback type, and feedback timing. It would be simplest to run 3 separate analyses. If you put it in one analysis, then you would be examining the effect of each predictor accounting for the effects of the other two. You can improve your question to get a good answer using the following guide: stats.meta.stackexchange.com/questions/1479/… $\endgroup$ – Kayle Sawyer Sep 14 '17 at 21:21

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.